Intra-Hour Photovoltaic Generation Forecasting Based on Multi-Source Data and Deep Learning Methods
Global issues pertaining to climate change have necessitated the rapid deployment of new energy sources, such as photovoltaic (PV) generation. In smart grids, accurate forecasting is essential to ensure the reliability and economy of the power system. However, PV generation is severely affected by meteorological factors, which hinders accurate forecasting. Various types of data, such as local measurement data, numerical weather prediction, and satellite images, can reflect meteorological dynamics over different time scales. This paper proposes a novel data-driven forecasting framework based on deep learning, which integrates an advanced U-net and an encoder-decoder architecture to cooperatively process multi-source (time series recording and satellite image) data.
Read More >
Data-Driven Engineering: The Reliability and Resilience of the North American Bulk Power System [Technology Leaders]
Electricity is an essential need for modern society. Nearly everything we do relies on safe and affordable electric energy. The constant demand for reliable energy delivery exists during a time of rapid changes to and evolutions of the bulk power system (BPS) in North America. Inverter-based resources, such as wind, solar photovoltaic (PV), battery energy storage systems, and hybrid plants, continue to transform the mix of BPS-connected generating resources. Sustainability and climate change initiatives are driving innovations in end-use loads, such as the electrification of the transportation sector.
Read More >
DAFT-E: Feature-Based Multivariate and Multi-Step-Ahead Wind Power Forecasting
At the recent 26th United Nations Climate Change Conference last year, more than 140 countries pledged to achieve net-zero emissions to combat climate change. And in a dramatic appeal to attain sustainability in the skies, Europe’s Flightpath 2050 initiated a bold effort to reduce CO2 emissions worldwide by 75%, NOx emissions by 90%, and the noise footprint by 60% by the midcentury mark.
Read More >